# Bundle Recommendation with Graph Convolutional Networks

arXiv: https://arxiv.org/abs/2005.03475 · HTML: https://mlsanity.com/paper/2005.03475/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2020.

## Built on by (most cited first, 24 of 24)

- [Large Language Models on Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2312.02783/) (2023)
- [Multimodal Recommender Systems: A Survey](https://mlsanity.com/paper/2302.03883/) (2023)
- [Multi-view Intent Disentangle Graph Networks for Bundle Recommendation](https://mlsanity.com/paper/2202.11425/) (2022)
- [Drug Package Recommendation via Interaction-aware Graph Induction](https://mlsanity.com/paper/2102.03577/) (2021)
- [Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Personalized Recommendation](https://mlsanity.com/paper/2109.02046/) (2021)
- [Bundle MCR: Towards Conversational Bundle Recommendation](https://mlsanity.com/paper/2207.12628/) (2022)
- [Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2202.09177/) (2022)
- [Adaptive In-Context Learning with Large Language Models for Bundle Generation](https://mlsanity.com/paper/2312.16262/) (2023)
- [Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems](https://mlsanity.com/paper/2106.04993/) (2021)
- [Cold-start Bundle Recommendation via Popularity-based Coalescence and Curriculum Heating](https://mlsanity.com/paper/2310.03813/) (2023)
- [Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters](https://mlsanity.com/paper/2210.15460/) (2022)
- [Bundle Recommendation with Item-level Causation-enhanced Multi-view Learning](https://mlsanity.com/paper/2408.08906/) (2024)
- [ComboShoppingBench: Evaluating LLM Agents for Budget-Constrained Basket Shopping with Coupons](https://mlsanity.com/paper/2608.09282/) (2026)
- [Does Knowledge Distillation Matter for Large Language Model based Bundle Generation?](https://mlsanity.com/paper/2504.17220/) (2025)
- [A Reproducibility Study of Product-side Fairness in Bundle Recommendation](https://mlsanity.com/paper/2507.14352/) (2025)
- [SkillSelect-Serve: QoS-Aware Budgeted Skill Service Recommendation for LLM Agents](https://mlsanity.com/paper/2607.00011/) (2026)
- [Session-aware Item-combination Recommendation with Transformer Network](https://mlsanity.com/paper/2111.07154/) (2021)
- [Gaussian Graph with Prototypical Contrastive Learning in E-Commerce Bundle Recommendation](https://mlsanity.com/paper/2307.13468/) (2023)
- [Adaptive spectral graph wavelets for collaborative filtering](https://mlsanity.com/paper/2312.03167/) (2023)
- [Hypergraph-Enhanced Dual Convolutional Network for Bundle Recommendation](https://mlsanity.com/paper/2312.11018/) (2023)
- [On a Scale-Invariant Approach to Bundle Recommendations in Candy Crush Saga](https://mlsanity.com/paper/2408.06799/) (2024)
- [Producer-Fairness in Sequential Bundle Recommendation](https://mlsanity.com/paper/2506.20329/) (2025)
- [Dual-Enhancement Product Bundling: Bridging Interactive Graph and Large Language Model](https://mlsanity.com/paper/2604.14030/) (2026)
- [RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents](https://mlsanity.com/paper/2605.18805/) (2026)

## Abstract (arXiv)

Bundle recommendation aims to recommend a bundle of items for a user to consume as a whole. Existing solutions integrate user-item interaction modeling into bundle recommendation by sharing model parameters or learning in a multi-task manner, which cannot explicitly model the affiliation between items and bundles, and fail to explore the decision-making when a user chooses bundles. In this work, we propose a graph neural network model named BGCN (short for textittextBFBundle textBFGraph textBFConvolutional textBFNetwork) for bundle recommendation. BGCN unifies user-item interaction, user-bundle interaction and bundle-item affiliation into a heterogeneous graph. With item nodes as the bridge, graph convolutional propagation between user and bundle nodes makes the learned representations capture the item level semantics. Through training based on hard-negative sampler, the user's fine-grained preferences for similar bundles are further distinguished. Empirical results on two real-world datasets demonstrate the strong performance gains of BGCN, which outperforms the state-of-the-art baselines by 10.77% to 23.18%.